Functional Generalized Structured Component Analysis

Hye Won Suk, Heungsun Hwang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

An extension of Generalized Structured Component Analysis (GSCA), called Functional GSCA, is proposed to analyze functional data that are considered to arise from an underlying smooth curve varying over time or other continua. GSCA has been geared for the analysis of multivariate data. Accordingly, it cannot deal with functional data that often involve different measurement occasions across participants and a large number of measurement occasions that exceed the number of participants. Functional GSCA addresses these issues by integrating GSCA with spline basis function expansions that represent infinite-dimensional curves onto a finite-dimensional space. For parameter estimation, functional GSCA minimizes a penalized least squares criterion by using an alternating penalized least squares estimation algorithm. The usefulness of functional GSCA is illustrated with gait data.

Original languageEnglish (US)
Pages (from-to)1-29
Number of pages29
JournalPsychometrika
DOIs
StateAccepted/In press - Oct 6 2016

Fingerprint

Least-Squares Analysis
Functional analysis
Gait
Splines
Parameter estimation
Multivariate Analysis
Penalized Least Squares
Functional Data
Alternating Least Squares
Curve
Least Squares Estimation
Spline Functions
Least Square Algorithm
Multivariate Data
Functional Analysis
Estimation Algorithms
Basis Functions
Parameter Estimation
Exceed
Continuum

Keywords

  • alternating least squares
  • basis function expansion
  • functional data analysis
  • generalized structured component analysis
  • penalized least squares
  • splines

ASJC Scopus subject areas

  • Psychology(all)
  • Applied Mathematics

Cite this

Functional Generalized Structured Component Analysis. / Suk, Hye Won; Hwang, Heungsun.

In: Psychometrika, 06.10.2016, p. 1-29.

Research output: Contribution to journalArticle

Suk, Hye Won ; Hwang, Heungsun. / Functional Generalized Structured Component Analysis. In: Psychometrika. 2016 ; pp. 1-29.
@article{14f4d7e078754875b83d884440216011,
title = "Functional Generalized Structured Component Analysis",
abstract = "An extension of Generalized Structured Component Analysis (GSCA), called Functional GSCA, is proposed to analyze functional data that are considered to arise from an underlying smooth curve varying over time or other continua. GSCA has been geared for the analysis of multivariate data. Accordingly, it cannot deal with functional data that often involve different measurement occasions across participants and a large number of measurement occasions that exceed the number of participants. Functional GSCA addresses these issues by integrating GSCA with spline basis function expansions that represent infinite-dimensional curves onto a finite-dimensional space. For parameter estimation, functional GSCA minimizes a penalized least squares criterion by using an alternating penalized least squares estimation algorithm. The usefulness of functional GSCA is illustrated with gait data.",
keywords = "alternating least squares, basis function expansion, functional data analysis, generalized structured component analysis, penalized least squares, splines",
author = "Suk, {Hye Won} and Heungsun Hwang",
year = "2016",
month = "10",
day = "6",
doi = "10.1007/s11336-016-9521-1",
language = "English (US)",
pages = "1--29",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",

}

TY - JOUR

T1 - Functional Generalized Structured Component Analysis

AU - Suk, Hye Won

AU - Hwang, Heungsun

PY - 2016/10/6

Y1 - 2016/10/6

N2 - An extension of Generalized Structured Component Analysis (GSCA), called Functional GSCA, is proposed to analyze functional data that are considered to arise from an underlying smooth curve varying over time or other continua. GSCA has been geared for the analysis of multivariate data. Accordingly, it cannot deal with functional data that often involve different measurement occasions across participants and a large number of measurement occasions that exceed the number of participants. Functional GSCA addresses these issues by integrating GSCA with spline basis function expansions that represent infinite-dimensional curves onto a finite-dimensional space. For parameter estimation, functional GSCA minimizes a penalized least squares criterion by using an alternating penalized least squares estimation algorithm. The usefulness of functional GSCA is illustrated with gait data.

AB - An extension of Generalized Structured Component Analysis (GSCA), called Functional GSCA, is proposed to analyze functional data that are considered to arise from an underlying smooth curve varying over time or other continua. GSCA has been geared for the analysis of multivariate data. Accordingly, it cannot deal with functional data that often involve different measurement occasions across participants and a large number of measurement occasions that exceed the number of participants. Functional GSCA addresses these issues by integrating GSCA with spline basis function expansions that represent infinite-dimensional curves onto a finite-dimensional space. For parameter estimation, functional GSCA minimizes a penalized least squares criterion by using an alternating penalized least squares estimation algorithm. The usefulness of functional GSCA is illustrated with gait data.

KW - alternating least squares

KW - basis function expansion

KW - functional data analysis

KW - generalized structured component analysis

KW - penalized least squares

KW - splines

UR - http://www.scopus.com/inward/record.url?scp=84990831657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990831657&partnerID=8YFLogxK

U2 - 10.1007/s11336-016-9521-1

DO - 10.1007/s11336-016-9521-1

M3 - Article

SP - 1

EP - 29

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

ER -